Lists pay-as-you-go unit prices for Hologres managed models, covering token-based, image-based, and video/audio-based models across supported regions.
Token-based model billing
Cache billing rules
For models that are billed by token, cached input tokens are charged at a fixed ratio of the input unit price. The following table describes the ratios.
|
Billing item |
Ratio to input unit price |
Description |
|
Explicit cache write |
Input unit price × 1.25 |
Charged when content is written to the cache for the first time. The price is 25% higher than that of a regular input token. |
|
Explicit cache hit |
Input unit price × 0.10 |
Charged when a request hits an existing explicit cache. The price is one tenth of that of a regular input token. |
|
Implicit cache hit |
Input unit price × 0.20 |
Charged when a request hits an implicit cache. The price is one fifth of that of a regular input token. |
For example, the input unit price of Qwen3.7-Max in the Singapore region is USD 0.00300 per 1,000 tokens. The cache prices are derived as follows:
-
Explicit cache write price = 0.00300 × 1.25 = USD 0.00375 per 1,000 tokens
-
Explicit cache hit price = 0.00300 × 0.10 = USD 0.00030 per 1,000 tokens
-
Implicit cache hit price = 0.00300 × 0.20 = USD 0.00060 per 1,000 tokens
|
Region |
Model name |
Model category |
Input token tier |
Input unit price (USD per 1,000 tokens) |
Output unit price (USD per 1,000 tokens) |
|
Qwen3.8-Max |
Text generation (non-thinking + thinking) |
- |
0.00198 |
0.00594 |
|
Qwen3.7-Max |
- |
0.00198 |
0.00594 |
||
|
Qwen3.7-Plus |
≤256K |
0.00034 |
0.00138 |
||
|
Qwen3.7-Plus |
256K~1M |
0.00103 |
0.00413 |
||
|
Qwen3.6-Plus |
≤256K |
0.00033 |
0.00198 |
||
|
Qwen3.6-Plus |
256K~1M |
0.00132 |
0.00792 |
||
|
Qwen3.6-Flash |
≤256K |
0.00020 |
0.00119 |
||
|
256K~1M |
0.00079 |
0.00475 |
|||
|
Qwen3-VL-Plus |
≤32K |
0.00017 |
0.00172 |
||
|
32K~128K |
0.00026 |
0.00258 |
|||
|
128K~256K |
0.00052 |
0.00516 |
|||
|
DeepSeek-V4-Pro |
- |
0.00198 |
0.00396 |
||
|
GLM-5.2 |
- |
0.00132 |
0.00462 |
||
|
DeepSeek-V4-Flash |
- |
0.00017 |
0.00033 |
||
|
Qwen-MT-Plus |
Translation |
- |
0.00031 |
0.00093 |
|
|
Text-Embedding-V4 |
Embedding |
- |
0.00009 |
- |
|
|
Qwen3.8-Max |
Text generation (non-thinking + thinking) |
- |
0.00240 |
0.00720 |
|
Qwen3.7-Max |
- |
0.00300 |
0.00900 |
||
|
Qwen3.7-Plus |
≤256K |
0.00048 |
0.00192 |
||
|
256K~1M |
0.00144 |
0.00576 |
|||
|
Qwen3.6-Plus |
≤256K |
0.00060 |
0.00360 |
||
|
256K~1M |
0.00240 |
0.00720 |
|||
|
Qwen3.6-Flash |
≤256K |
0.00030 |
0.00180 |
||
|
256K~1M |
0.00120 |
0.00480 |
|||
|
Qwen3-VL-Plus |
≤32K |
0.00024 |
0.00192 |
||
|
32K~128K |
0.00036 |
0.00288 |
|||
|
128K~256K |
0.00072 |
0.00576 |
|||
|
DeepSeek-V4-Pro |
- |
0.00288 |
0.00576 |
||
|
GLM-5.2 |
- |
0.00168 |
0.00528 |
||
|
DeepSeek-V4-Flash |
- |
0.00024 |
0.00048 |
||
|
Qwen-MT-Plus |
Translation |
- |
0.00295 |
0.00884 |
|
|
Text-Embedding-V4 |
Embedding |
- |
0.00008 |
- |
Image-based model billing
International site pricing (Unit: USD per image)
|
Region |
Model name |
Model category |
Unit price (USD per image) |
|
Qwen-Image-2.0-Pro |
Image generation/editing |
0.086011 |
|
Qwen-Image-2.0-Pro |
0.0900 |
Video and audio model billing
|
Region |
Model name |
Billing rule |
Resolution/Specification |
Unit price (USD per second) |
|
Fun-ASR |
Billed by audio duration |
- |
0.000038 |
|
Wan2.7-T2V |
Billed per second of output video |
720P |
0.103214 |
|
|
1080P |
0.172024 |
|||
|
Wan2.7-I2V |
Billed per second of output video |
720P |
0.103214 |
|
|
1080P |
0.172024 |
|||
|
Wan2.7-R2V |
Billed per second for both input and output video |
720P |
0.086012 |
|
|
1080P |
0.143353 |
|||
|
Wan2.7-VideoEdit |
Billed per second for both input and output video |
720P |
0.103214 |
|
|
1080P |
0.172024 |
|||
|
HappyHorse-1.0-T2V |
Billed per second of output video |
720P |
0.148523 |
|
|
1080P |
0.264041 |
|||
|
HappyHorse-1.0-I2V |
Billed per second of output video |
720P |
0.148523 |
|
|
1080P |
0.264041 |
|||
|
HappyHorse-1.0-R2V |
Billed per second of output video |
720P |
0.148523 |
|
|
1080P |
0.264041 |
|||
|
HappyHorse-1.0-VideoEdit |
Billed per second for both input and output video |
720P |
0.148523 |
|
|
1080P |
0.264041 |
|||
|
HappyHorse-1.1-T2V |
Billed per second of output video |
720P |
0.148523 |
|
|
1080P |
0.198031 |
|||
|
HappyHorse-1.1-I2V |
Billed per second of output video |
720P |
0.148523 |
|
|
1080P |
0.198031 |
|||
|
HappyHorse-1.1-R2V |
Billed per second of output video |
720P |
0.148523 |
|
|
1080P |
0.198031 |
|||
|
Fun-ASR |
Billed by audio duration |
- |
0.000042 |
|
Wan2.7-T2V |
Billed per second of output video |
720P |
0.120000 |
|
|
1080P |
0.180000 |
|||
|
Wan2.7-I2V |
Billed per second of output video |
720P |
0.120000 |
|
|
1080P |
0.180000 |
|||
|
Wan2.7-R2V |
Billed per second for both input and output video |
720P |
0.120000 |
|
|
1080P |
0.180000 |
|||
|
Wan2.7-VideoEdit |
Billed per second for both input and output video |
720P |
0.1200 |
|
|
1080P |
0.1800 |
|||
|
HappyHorse-1.0-T2V |
Billed per second of output video |
720P |
0.168000 |
|
|
1080P |
0.288000 |
|||
|
HappyHorse-1.0-I2V |
Billed per second of output video |
720P |
0.168000 |
|
|
1080P |
0.288000 |
|||
|
HappyHorse-1.0-R2V |
Billed per second of output video |
720P |
0.168000 |
|
|
1080P |
0.288000 |
|||
|
HappyHorse-1.0-VideoEdit |
Billed per second for both input and output video |
720P |
0.168000 |
|
|
1080P |
0.288000 |
|||
|
HappyHorse-1.1-T2V |
Billed per second of output video |
720P |
0.168000 |
|
|
1080P |
0.216000 |
|||
|
HappyHorse-1.1-I2V |
Billed per second of output video |
720P |
0.168000 |
|
|
1080P |
0.216000 |
|||
|
HappyHorse-1.1-R2V |
Billed per second of output video |
720P |
0.168000 |
|
|
1080P |
0.216000 |